Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3094 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.7101. Min Act: -0.0000

Data Index: 738014 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.5010. Min Act: -0.0000

Data Index: 1256881 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.4311. Min Act: -0.0000

Data Index: 481299 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.4158. Min Act: -0.0000

Data Index: 520440 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.1709. Min Act: -0.0001

Data Index: 639203 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.2971. Min Act: -0.0001

Data Index: 1219731 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.0113. Min Act: -0.0001

Data Index: 368432 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 2.7101. Min Range: -2.7101

Max Act: 1.8902. Min Act: -0.0001

Data Index: 1086664 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 2.7101. Min Range: -2.7101

Max Act: 1.9708. Min Act: -0.0001

Data Index: 508994 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 2.7101. Min Range: -2.7101

Max Act: 1.9448. Min Act: -0.0000

Data Index: 1194291 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 2.7101. Min Range: -2.7101

Max Act: 1.9250. Min Act: -0.0001

Data Index: 1326788 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.0179. Min Act: -0.0001

Data Index: 834883 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 2.7101. Min Range: -2.7101

Max Act: 1.9129. Min Act: -0.0001

Data Index: 833771 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 2.7101. Min Range: -2.7101

Max Act: 1.8091. Min Act: -0.0001

Data Index: 751070 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 2.7101. Min Range: -2.7101

Max Act: 1.9716. Min Act: -0.0000

Data Index: 526273 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 2.7101. Min Range: -2.7101

Max Act: 1.9254. Min Act: -0.0000

Data Index: 383231 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 2.7101. Min Range: -2.7101

Max Act: 1.9200. Min Act: -0.0000

Data Index: 1239032 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 2.7101. Min Range: -2.7101

Max Act: 2.0339. Min Act: -0.0000

Data Index: 1202178 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 2.7101. Min Range: -2.7101

Max Act: 1.8045. Min Act: -0.0001

Data Index: 39725 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 2.7101. Min Range: -2.7101

Max Act: 1.7125. Min Act: -0.0001

Data Index: 412943 (C4 (Web Text))

Max Activating Token Index: 170